Mistral AI releases Timestral, a family of time-series foundation models

What happened

Mistral AI released Timestral in four sizes, from 5M to 209M parameters, for probabilistic, multivariate forecasting with past-only and known-future covariates. Mistral reports that its 209M model ranks first among pretrained, zero-shot models across five metrics on GIFT-Eval, TIME and fev-bench, using a single checkpoint without ensembling. All sizes support CPU inference, and Mistral published a GitHub repository for running Timestral on users’ data; domain adaptation and fine-tuning are available through Mistral Forge.

The story so far

Mistral AI released Timestral, a family of time-series forecasting models in four sizes ranging from 5M to 209M parameters, and published a GitHub repository for users to run them on their own data. All four sizes support CPU inference. The models produce probabilistic forecasts for multiple variables and can use both past-only inputs and inputs whose future values are known. Mistral says the 209M model ranks first among pretrained, zero-shot models across five metrics on GIFT-Eval, TIME and fev-bench, using a single checkpoint without ensembling. Organizations can also use Mistral Forge for domain adaptation and fine-tuning.

Keep reading

Trending now

1. 1Meta Releases Muse Spark Open With Mac and Cloud Support, Topping US Open-Weight Index
2. 2Google Launches Gemini 4 Argon Globally, Expands Paid Access as Benchmark Results Vary
3. 3OpenAI Updates GPT-6 Astra Pro in ChatGPT With Parallel Agents and Faster Responses
4. 4Meta’s New Business Terms Raise Dispute Over Website Crawling and AI Training Rights